Skip to main content
Glama

RuntimeGetDumpById

Read a specific ABAP runtime dump by its ID to view full content, summary, or formatted details for analysis.

Instructions

[runtime] Read a specific ABAP runtime dump by its ID. First use RuntimeListFeeds to find dumps and get their IDs, then pass dump_id here to read the full dump content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dump_idYesFull runtime dump ID (e.g. from RuntimeListFeeds).
viewNoDump view mode: default payload, summary section, or formatted long text.default
response_modeNoControls what is returned: "payload" — full parsed dump data, "summary" — compact key facts only (title, exception, program, line, user, date…), "both" — summary + full payload.both

Implementation Reference

  • Main handler function that reads a specific ABAP runtime dump by its ID using AdtRuntimeClient, parses the payload to JSON, optionally extracts a summary of key facts, and returns the result based on the response_mode parameter.
    export async function handleRuntimeGetDumpById(
      context: HandlerContext,
      args: RuntimeGetDumpByIdArgs,
    ) {
      const { connection, logger } = context;
    
      try {
        const dumpId = args?.dump_id?.trim();
    
        if (!dumpId) {
          throw new Error(
            'dump_id is required. Use RuntimeListFeeds to find dump IDs first.',
          );
        }
    
        const view = args.view ?? 'default';
        const responseMode = args.response_mode ?? 'both';
        const runtimeClient = new AdtRuntimeClient(connection, logger);
        const response = await runtimeClient.getDumps().getById(dumpId, { view });
        const parsedPayload = parseRuntimePayloadToJson(response.data);
    
        const result: Record<string, unknown> = {
          success: true,
          dump_id: dumpId,
          view,
          status: response.status,
        };
    
        if (responseMode === 'summary' || responseMode === 'both') {
          const summary: Record<string, unknown> = {};
          collectKeyFacts(parsedPayload, summary);
          result.summary = summary;
        }
    
        if (responseMode === 'payload' || responseMode === 'both') {
          result.payload = parsedPayload;
        }
    
        return return_response({
          data: JSON.stringify(result, null, 2),
          status: response.status,
          statusText: response.statusText,
          headers: response.headers,
          config: response.config,
        });
      } catch (error: any) {
        logger?.error('Error reading runtime dump by ID:', error);
        return return_error(error);
      }
    }
  • Tool definition including name 'RuntimeGetDumpById', inputSchema with dump_id (required), view, and response_mode parameters.
    export const TOOL_DEFINITION = {
      name: 'RuntimeGetDumpById',
      available_in: ['onprem', 'cloud'] as const,
      description:
        '[runtime] Read a specific ABAP runtime dump by its ID. First use RuntimeListFeeds to find dumps and get their IDs, then pass dump_id here to read the full dump content.',
      inputSchema: {
        type: 'object',
        properties: {
          dump_id: {
            type: 'string',
            description: 'Full runtime dump ID (e.g. from RuntimeListFeeds).',
          },
          view: {
            type: 'string',
            enum: ['default', 'summary', 'formatted'],
            description:
              'Dump view mode: default payload, summary section, or formatted long text.',
            default: 'default',
          },
          response_mode: {
            type: 'string',
            enum: ['payload', 'summary', 'both'],
            description:
              'Controls what is returned: "payload" — full parsed dump data, "summary" — compact key facts only (title, exception, program, line, user, date…), "both" — summary + full payload.',
            default: 'both',
          },
        },
        required: ['dump_id'],
      },
    } as const;
  • TypeScript interface RuntimeGetDumpByIdArgs defining the types for the input arguments.
    interface RuntimeGetDumpByIdArgs {
      dump_id: string;
      view?: 'default' | 'summary' | 'formatted';
      response_mode?: 'payload' | 'summary' | 'both';
    }
  • Import of handleRuntimeGetDumpById and its TOOL_DEFINITION from the handler file.
    import {
      handleRuntimeGetDumpById,
      TOOL_DEFINITION as RuntimeGetDumpById_Tool,
    } from '../../../handlers/system/readonly/handleRuntimeGetDumpById';
  • Registration of RuntimeGetDumpById_Tool and its handler in the SystemHandlersGroup.
    {
      toolDefinition: RuntimeGetDumpById_Tool,
      handler: (args: any) => handleRuntimeGetDumpById(this.context, args),
    },
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must stand alone. It states the tool is a read operation ('Read'), which is safe, but it does not detail any side effects, permissions, rate limits, or other behavioral traits. The mention of 'full dump content' gives some idea of the output, but more context would be beneficial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise—just two sentences. The first sentence clearly states the purpose, and the second provides critical usage guidance. Every word earns its place; no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with three parameters and no output schema, the description is adequate but not complete. It hints at 'full dump content' but does not explain the varied return formats controlled by response_mode. Given the many sibling runtime tools, more differentiation would help, but the description does cover the essential workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters already have good descriptions. The description adds value by explicitly linking dump_id to RuntimeListFeeds, enhancing understanding. For view and response_mode, the schema already explains options and defaults; no additional semantics are provided in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Read a specific ABAP runtime dump by its ID.' It specifies the resource (runtime dump) and the verb (read), and distinguishes it from siblings like RuntimeListFeeds by indicating that RuntimeListFeeds should be used first to obtain the dump ID.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool: after using RuntimeListFeeds to find dumps and get their IDs. It implies a workflow but does not explicitly list when not to use it or alternatives, though the context with siblings is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fr0ster/mcp-abap-adt'

If you have feedback or need assistance with the MCP directory API, please join our Discord server